Oversampling

Class Imbalance

वर्ग असन्तुलन

When some categories have far more examples than others, biasing a model.

Activation Function

एक्टिभेसन फंक्सन

A function that decides whether and how strongly a neuron fires, adding non-linearity.

Active Learning

सक्रिय सिकाइ

A method where the model selects the most useful examples for humans to label.

Autoscaling

अटोस्केलिङ

Automatically adding or removing computing resources as demand changes.

Benchmark

बेन्चमार्क / मापदण्ड

A standard dataset or test used to compare the performance of different models.

Bias-Variance Tradeoff

बायस-भेरियन्स सन्तुलन

The balance between a model being too simple (high bias) and too sensitive to data (high variance).

Confusion Matrix

कन्फ्युजन म्याट्रिक्स

A table showing correct and incorrect predictions broken down by class.

Cross-Validation

क्रस-भ्यालिडेसन

A technique that splits data into multiple parts to test a model more reliably.